Staff Engineer

LeadSquared; Bengaluru; On-site; INR 4,500,000 - 7,500,000; Full time

Job summary

LeadSquared is hiring a Staff Engineer to lead the backend and AI architecture of Lumen. You will design and ship multi-agent systems, combining Python backend engineering with GenAI work across LLMs and vector databases.

This high-ownership role requires setting technical direction, writing production code, and raising the engineering bar for the team. You will mentor engineers and partner with product and design to deliver AI features at scale.

Qualifications

• 6–8 years of backend software experience.
• Expert-level Python, including async frameworks.
• Experience building multi-agent systems in production.
• Hands-on with LLMs, prompt engineering, function calling.
• Proven experience with end-to-end RAG systems.
• Experience with vector databases (Pinecone, Weaviate, etc.).
• Practical MCP (Model Context Protocol) experience.
• Strong grounding in distributed systems and microservices.
• Cloud platforms, Docker and Kubernetes experience.
• Track record of leading design and mentoring engineers.

Responsibilities

• Architect and scale multi-agent systems for Lumen.
• Design Python backend services and APIs for production scale.
• Build retrieval-augmented generation (RAG) pipelines with embeddings and vector DBs.
• Integrate agents with MCP and tool interfaces across LeadSquared platform.
• Select LLMs, drive prompts and cost‑latency trade‑offs.
• Set up evaluation, guardrails and observability for agent quality and safety.
• Lead architectural decisions spanning multiple teams.
• Mentor engineers and establish GenAI best practices.
• Collaborate with product and design to ship AI features.

Skills

Backend Python

Async programming

Distributed systems

Microservices

LLMs

RAG pipelines

Design reviews

Mentoring engineers

Product collaboration

Tools

FastAPI

Django

Flask

LangGraph

CrewAI

AutoGen

Pinecone

Weaviate

Qdrant

Milvus

pgvector

Docker

Kubernetes

Job description

About LeadSquared and Lumen

We’re building the next generation of AI-powered business software, and we’re looking for people who want to shape that future with us.

With Lumen, we’re reimagining how users interact with CRM—moving beyond screens, menus and dashboards to an intelligent interface where users can simply ask AI to take actions, retrieve knowledge, generate insights and get work done.

With Agent Studio, we’re enabling businesses to build, test and deploy their own AI agents for real-world workflows.

The role

We are hiring a Staff Engineer to lead the backend and AI architecture of Lumen. You will design and ship the multi-agent systems that power Lumen, combining deep Python backend engineering with hands‑on GenAI work across LLMs, RAG, vector databases and MCP.

This is a high‑ownership, hands‑on technical leadership role. You will set the technical direction, write production code, and raise the engineering bar for the team.

Key responsibilities

• Architect, build and scale multi‑agent systems for Lumen, including agent orchestration, planning, tool use and memory.
• Design and own Python backend services and APIs that are reliable, secure and performant at production scale.
• Build retrieval‑augmented generation (RAG) pipelines: ingestion, chunking, embeddings, hybrid search and re‑ranking on vector databases.
• Integrate agents with LeadSquared's platform and third‑party tools through the Model Context Protocol (MCP) and well‑defined tool interfaces.
• Select and evaluate LLMs, and drive prompt design, fine‑tuning decisions and cost‑latency trade‑offs.
• Set up evaluation frameworks, guardrails and observability for agent quality, hallucination, safety and reliability.
• Lead technical design reviews and make architectural decisions that span multiple teams.
• Mentor senior and mid‑level engineers, and establish engineering best practices for GenAI development.
• Partner with product, design and customer‑facing teams to turn customer problems into shipped AI features.

Must‑have qualifications

• 6–8 years of software engineering experience, with a strong focus on backend development.
• Expert‑level Python, including async programming and frameworks such as FastAPI, Django or Flask.
• Currently building multi‑agent or agentic systems in production, using frameworks such as LangGraph, CrewAI, AutoGen or custom orchestration.
• Hands‑on experience with LLMs (OpenAI, Anthropic, open‑source models), including prompt engineering, function calling and structured outputs.
• Proven experience building RAG systems end to end.
• Working experience with vector databases such as Pinecone, Weaviate, Qdrant, Milvus, pgvector or Elasticsearch.
• Practical experience with the Model Context Protocol (MCP), building or consuming MCP servers and tools.
• Solid grounding in distributed systems, microservices, databases (SQL and NoSQL), caching and message queues.
• Experience with cloud platforms (AWS, GCP or Azure), Docker and Kubernetes.
• Track record of leading technical design and mentoring engineers.

Good to have

• Experience building customer‑facing applications, especially conversational or AI‑assisted products used by business users.
• Background in SaaS, CRM or sales and marketing technology.
• Experience with LLM evaluation and observability tools such as LangSmith, Langfuse, Ragas or Arize.
• Familiarity with fine‑tuning, embeddings optimisation or knowledge graphs.
• Experience shipping AI features in a multi‑tenant environment with strong data privacy and security requirements.
• Contributions to open‑source GenAI projects, publications or talks.
• Shape the core architecture of an agentic AI product at an early, high‑impact stage.
• Work on real GenAI problems at scale, with production traffic from businesses that rely on LeadSquared every day.
• Own decisions end to end, from model choice and agent design to how features reach customers.
• Grow as a technical leader alongside a team that ships fast and learns fast.